no code implementations • 17 Oct 2024 • Allison Lau, Younwoo Choi, Vahid Balazadeh, Keertana Chidambaram, Vasilis Syrgkanis, Rahul G. Krishnan

Reinforcement Learning from Human Feedback (RLHF) is widely used to align Language Models (LMs) with human preferences.

no code implementations • 4 Jun 2024 • Justin Whitehouse, Christopher Jung, Vasilis Syrgkanis, Bryan Wilder, Zhiwei Steven Wu

Our bounds involve two decoupled terms - one measuring the error in estimating the unknown nuisance parameters, and the other representing the calibration error in a hypothetical world where the learned nuisance estimates were true.

no code implementations • 24 May 2024 • Jiyuan Tan, Jose Blanchet, Vasilis Syrgkanis

Recent progress in Neural Causal Models (NCMs) showcased how identification and partial identification of causal effects can be automatically carried out via training of neural generative models that respect the constraints encoded in a given causal graph [Xia et al. 2022, Balazadeh et al. 2022].

no code implementations • 23 May 2024 • Keertana Chidambaram, Karthik Vinay Seetharaman, Vasilis Syrgkanis

We then introduce a min-max regret ensemble learning model to produce a single generative method to minimize worst-case regret among annotator subgroups with similar latent factors.

no code implementations • 13 May 2024 • David M. Ritzwoller, Vasilis Syrgkanis

The intervals are built around a class of nonparametric regression algorithms based on subsampled kernels.

1 code implementation • 8 May 2024 • Jabari Hastings, Christopher Jung, Charlotte Peale, Vasilis Syrgkanis

A rich line of recent work has studied distributionally robust learning approaches that seek to learn a hypothesis that performs well, in the worst-case, on many different distributions over a population.

no code implementations • 2 May 2024 • Ravi B. Sojitra, Vasilis Syrgkanis

We consider Dynamic Treatment Regimes (DTRs) with One Sided Noncompliance that arise in applications such as digital recommendations and adaptive medical trials.

1 code implementation • 10 Apr 2024 • Vahid Balazadeh, Keertana Chidambaram, Viet Nguyen, Rahul G. Krishnan, Vasilis Syrgkanis

We study the problem of online sequential decision-making given auxiliary demonstrations from experts who made their decisions based on unobserved contextual information.

no code implementations • 7 Mar 2024 • Zihao Li, Hui Lan, Vasilis Syrgkanis, Mengdi Wang, Masatoshi Uehara

In this paper, we study nonparametric estimation of instrumental variable (IV) regressions.

1 code implementation • 4 Mar 2024 • Victor Chernozhukov, Christian Hansen, Nathan Kallus, Martin Spindler, Vasilis Syrgkanis

An introduction to the emerging fusion of machine learning and causal inference.

no code implementations • 22 Feb 2024 • Jikai Jin, Vasilis Syrgkanis

Average treatment effect estimation is the most central problem in causal inference with application to numerous disciplines.

no code implementations • 26 Dec 2023 • Daniel Ngo, Keegan Harris, Anish Agarwal, Vasilis Syrgkanis, Zhiwei Steven Wu

We consider the setting of synthetic control methods (SCMs), a canonical approach used to estimate the treatment effect on the treated in a panel data setting.

no code implementations • 5 Dec 2023 • Yash Chandak, Shiv Shankar, Vasilis Syrgkanis, Emma Brunskill

Indirect experiments provide a valuable framework for estimating treatment effects in situations where conducting randomized control trials (RCTs) is impractical or unethical.

no code implementations • 21 Nov 2023 • Jikai Jin, Vasilis Syrgkanis

In this work, we provide the first identifiability results based on data that stem from general environments.

no code implementations • 25 Oct 2023 • Hui Lan, Vasilis Syrgkanis

We provide regret rates for the major existing CATE ensembling approaches and propose a new CATE model ensembling approach based on Q-aggregation using the doubly robust loss.

no code implementations • 25 Jul 2023 • Andrew Bennett, Nathan Kallus, Xiaojie Mao, Whitney Newey, Vasilis Syrgkanis, Masatoshi Uehara

We consider estimation of parameters defined as linear functionals of solutions to linear inverse problems.

1 code implementation • 8 Mar 2023 • Qizhao Chen, Morgane Austern, Vasilis Syrgkanis

Estimating optimal dynamic policies from offline data is a fundamental problem in dynamic decision making.

1 code implementation • 17 Feb 2023 • Vasilis Syrgkanis, Ruohan Zhan

Our goal is to evaluate a counterfactual policy post-data collection and estimate structural parameters, like dynamic treatment effects, which can be used for credit assignment and determining the effect of earlier actions on final outcomes.

no code implementations • 10 Feb 2023 • Andrew Bennett, Nathan Kallus, Xiaojie Mao, Whitney Newey, Vasilis Syrgkanis, Masatoshi Uehara

In this paper, we study nonparametric estimation of instrumental variable (IV) regressions.

1 code implementation • 3 Nov 2022 • Divyat Mahajan, Ioannis Mitliagkas, Brady Neal, Vasilis Syrgkanis

We study the problem of model selection in causal inference, specifically for conditional average treatment effect (CATE) estimation.

no code implementations • 20 Oct 2022 • Anish Agarwal, Vasilis Syrgkanis

Our work avoids the combinatorial explosion in the number of units that would be required by a vanilla application of prior synthetic control and synthetic intervention methods in such dynamic treatment regime settings.

1 code implementation • 14 Oct 2022 • Vahid Balazadeh, Vasilis Syrgkanis, Rahul G. Krishnan

We propose a new method for partial identification of average treatment effects(ATEs) in general causal graphs using implicit generative models comprising continuous and discrete random variables.

no code implementations • 17 Aug 2022 • Andrew Bennett, Nathan Kallus, Xiaojie Mao, Whitney Newey, Vasilis Syrgkanis, Masatoshi Uehara

In a variety of applications, including nonparametric instrumental variable (NPIV) analysis, proximal causal inference under unmeasured confounding, and missing-not-at-random data with shadow variables, we are interested in inference on a continuous linear functional (e. g., average causal effects) of nuisance function (e. g., NPIV regression) defined by conditional moment restrictions.

no code implementations • 3 Jun 2022 • Qizhao Chen, Vasilis Syrgkanis, Morgane Austern

For instance, we show that the stability properties that we propose are satisfied for ensemble bagged estimators, built via sub-sampling without replacement, a popular technique in machine learning practice.

1 code implementation • 10 Apr 2022 • Kartik Ahuja, Divyat Mahajan, Vasilis Syrgkanis, Ioannis Mitliagkas

In this work, we depart from these assumptions and ask: a) How can we get disentanglement when the auxiliary information does not provide conditional independence over the factors of variation?

no code implementations • 25 Mar 2022 • Victor Chernozhukov, Whitney Newey, Rahul Singh, Vasilis Syrgkanis

We extend the idea of automated debiased machine learning to the dynamic treatment regime and more generally to nested functionals.

1 code implementation • 26 Dec 2021 • Victor Chernozhukov, Carlos Cinelli, Whitney Newey, Amit Sharma, Vasilis Syrgkanis

We develop a general theory of omitted variable bias for a wide range of common causal parameters, including (but not limited to) averages of potential outcomes, average treatment effects, average causal derivatives, and policy effects from covariate shifts.

no code implementations • NeurIPS 2021 • Morgane Austern, Vasilis Syrgkanis

One of the most commonly used methods for forming confidence intervals is the empirical bootstrap, which is especially expedient when the limiting distribution of the estimator is unknown.

no code implementations • NeurIPS 2021 • Greg Lewis, Vasilis Syrgkanis

We consider the estimation of treatment effects in settings when multiple treatments are assigned over time and treatments can have a causal effect on future outcomes.

1 code implementation • 6 Oct 2021 • Victor Chernozhukov, Whitney K. Newey, Victor Quintas-Martinez, Vasilis Syrgkanis

We also propose a Random Forest method which learns a locally linear representation of the Riesz function.

no code implementations • 6 Oct 2021 • Dhruv Rohatgi, Vasilis Syrgkanis

For many inference problems in statistics and econometrics, the unknown parameter is identified by a set of moment conditions.

1 code implementation • 27 Aug 2021 • Amit Sharma, Vasilis Syrgkanis, Cheng Zhang, Emre Kiciman

Estimation of causal effects involves crucial assumptions about the data-generating process, such as directionality of effect, presence of instrumental variables or mediators, and whether all relevant confounders are observed.

1 code implementation • 21 Jul 2021 • Daniel Ngo, Logan Stapleton, Vasilis Syrgkanis, Zhiwei Steven Wu

In rounds, a social planner interacts with a sequence of heterogeneous agents who arrive with their unobserved private type that determines both their prior preferences across the actions (e. g., control and treatment) and their baseline rewards without taking any treatment.

1 code implementation • ICLR 2021 • Tri Dao, Govinda M Kamath, Vasilis Syrgkanis, Lester Mackey

A popular approach to model compression is to train an inexpensive student model to mimic the class probabilities of a highly accurate but cumbersome teacher model.

no code implementations • NeurIPS 2021 • Keith Battocchi, Eleanor Dillon, Maggie Hei, Greg Lewis, Miruna Oprescu, Vasilis Syrgkanis

Policy makers typically face the problem of wanting to estimate the long-term effects of novel treatments, while only having historical data of older treatment options.

no code implementations • 12 Mar 2021 • Jann Spiess, Vasilis Syrgkanis, Victor Yaneng Wang

In this paper, we propose a machine-learning method that is specifically optimized for finding such subgroups in noisy data.

no code implementations • 30 Dec 2020 • Victor Chernozhukov, Whitney Newey, Rahul Singh, Vasilis Syrgkanis

Many causal parameters are linear functionals of an underlying regression.

no code implementations • 23 Nov 2020 • Morgane Austern, Vasilis Syrgkanis

One of the most commonly used methods for forming confidence intervals for statistical inference is the empirical bootstrap, which is especially expedient when the limiting distribution of the estimator is unknown.

no code implementations • 26 Jul 2020 • Gali Noti, Vasilis Syrgkanis

We consider the problem of bid prediction in repeated auctions and evaluate the performance of econometric methods for learning agents using a dataset from a mainstream sponsored search auction marketplace.

no code implementations • 7 Jul 2020 • Vasilis Syrgkanis, Manolis Zampetakis

We prove that if only $r$ of the $d$ features are relevant for the mean outcome function, then shallow trees built greedily via the CART empirical MSE criterion achieve MSE rates that depend only logarithmically on the ambient dimension $d$.

1 code implementation • NeurIPS 2020 • Nishanth Dikkala, Greg Lewis, Lester Mackey, Vasilis Syrgkanis

We develop an approach for estimating models described via conditional moment restrictions, with a prototypical application being non-parametric instrumental variable regression.

no code implementations • 17 Feb 2020 • Greg Lewis, Vasilis Syrgkanis

We consider the estimation of treatment effects in settings when multiple treatments are assigned over time and treatments can have a causal effect on future outcomes or the state of the treated unit.

no code implementations • 15 Oct 2019 • Annie Liang, Xiaosheng Mu, Vasilis Syrgkanis

An agent has access to multiple information sources, each of which provides information about a different attribute of an unknown state.

1 code implementation • NeurIPS 2019 • Mert Demirer, Vasilis Syrgkanis, Greg Lewis, Victor Chernozhukov

Our results also apply if the model does not satisfy our semi-parametric form, but rather we measure regret in terms of the best projection of the true value function to this functional space.

2 code implementations • NeurIPS 2019 • Vasilis Syrgkanis, Victor Lei, Miruna Oprescu, Maggie Hei, Keith Battocchi, Greg Lewis

We develop a statistical learning approach to the estimation of heterogeneous effects, reducing the problem to the minimization of an appropriate loss function that depends on a set of auxiliary models (each corresponding to a separate prediction task).

3 code implementations • 25 Jan 2019 • Dylan J. Foster, Vasilis Syrgkanis

We provide non-asymptotic excess risk guarantees for statistical learning in a setting where the population risk with respect to which we evaluate the target parameter depends on an unknown nuisance parameter that must be estimated from data.

1 code implementation • 11 Jan 2019 • Khashayar Khosravi, Greg Lewis, Vasilis Syrgkanis

We show that if the intrinsic dimension of the covariate distribution is equal to $d$, then the finite sample estimation error of our estimator is of order $n^{-1/(d+2)}$ and our estimate is $n^{1/(d+2)}$-asymptotically normal, irrespective of $D$.

3 code implementations • 13 Jun 2018 • Denis Nekipelov, Vira Semenova, Vasilis Syrgkanis

This paper proposes a Lasso-type estimator for a high-dimensional sparse parameter identified by a single index conditional moment restriction (CMR).

1 code implementation • 9 Jun 2018 • Miruna Oprescu, Vasilis Syrgkanis, Zhiwei Steven Wu

We provide a consistency rate and establish asymptotic normality for our estimator.

1 code implementation • 19 Mar 2018 • Greg Lewis, Vasilis Syrgkanis

We provide an approach for learning deep neural net representations of models described via conditional moment restrictions.

1 code implementation • 13 Mar 2018 • Jimmy Wu, Diondra Peck, Scott Hsieh, Vandana Dialani, Constance D. Lehman, Bolei Zhou, Vasilis Syrgkanis, Lester Mackey, Genevieve Patterson

This work interprets the internal representations of deep neural networks trained for classification of diseased tissue in 2D mammograms.

2 code implementations • ICML 2018 • Akshay Krishnamurthy, Zhiwei Steven Wu, Vasilis Syrgkanis

This paper studies semiparametric contextual bandits, a generalization of the linear stochastic bandit problem where the reward for an action is modeled as a linear function of known action features confounded by an non-linear action-independent term.

1 code implementation • NeurIPS 2019 • Jonas Mueller, Vasilis Syrgkanis, Matt Taddy

We consider dynamic pricing with many products under an evolving but low-dimensional demand model.

1 code implementation • ICML 2018 • Yash Deshpande, Lester Mackey, Vasilis Syrgkanis, Matt Taddy

Estimators computed from adaptively collected data do not behave like their non-adaptive brethren.

no code implementations • NeurIPS 2017 • Darrell Hoy, Denis Nekipelov, Vasilis Syrgkanis

The notion of the price of anarchy takes a worst-case stance to efficiency analysis, considering instance independent guarantees of efficiency.

1 code implementation • 3 Nov 2017 • Zhe Feng, Chara Podimata, Vasilis Syrgkanis

We address online learning in complex auction settings, such as sponsored search auctions, where the value of the bidder is unknown to her, evolving in an arbitrary manner and observed only if the bidder wins an allocation.

1 code implementation • ICML 2018 • Lester Mackey, Vasilis Syrgkanis, Ilias Zadik

Double machine learning provides $\sqrt{n}$-consistent estimates of parameters of interest even when high-dimensional or nonparametric nuisance parameters are estimated at an $n^{-1/4}$ rate.

1 code implementation • ICLR 2018 • Constantinos Daskalakis, Andrew Ilyas, Vasilis Syrgkanis, Haoyang Zeng

Moreover, we show that optimistic mirror decent addresses the limit cycling problem in training WGANs.

no code implementations • 10 Oct 2017 • Vasilis Syrgkanis, Elie Tamer, Juba Ziani

Given a sample of bids from independent auctions, this paper examines the question of inference on auction fundamentals (e. g. valuation distributions, welfare measures) under weak assumptions on information structure.

no code implementations • NeurIPS 2017 • Robert Chen, Brendan Lucier, Yaron Singer, Vasilis Syrgkanis

We consider robust optimization problems, where the goal is to optimize in the worst case over a class of objective functions.

no code implementations • 12 Apr 2017 • Vasilis Syrgkanis

We consider two stage estimation with a non-parametric first stage and a generalized method of moments second stage, in a simpler setting than (Chernozhukov et al. 2016).

no code implementations • NeurIPS 2017 • Vasilis Syrgkanis

We introduce a new sample complexity measure, which we refer to as split-sample growth rate.

no code implementations • 18 Mar 2017 • Annie Liang, Xiaosheng Mu, Vasilis Syrgkanis

We consider the problem of optimal dynamic information acquisition from many correlated information sources.

no code implementations • 5 Nov 2016 • Miroslav Dudík, Nika Haghtalab, Haipeng Luo, Robert E. Schapire, Vasilis Syrgkanis, Jennifer Wortman Vaughan

We consider the design of computationally efficient online learning algorithms in an adversarial setting in which the learner has access to an offline optimization oracle.

no code implementations • 26 Jul 2016 • Tim Roughgarden, Vasilis Syrgkanis, Eva Tardos

This survey outlines a general and modular theory for proving approximation guarantees for equilibria of auctions in complex settings.

no code implementations • NeurIPS 2016 • Vasilis Syrgkanis, Haipeng Luo, Akshay Krishnamurthy, Robert E. Schapire

We give an oracle-based algorithm for the adversarial contextual bandit problem, where either contexts are drawn i. i. d.

no code implementations • 24 Feb 2016 • Yishay Mansour, Aleksandrs Slivkins, Vasilis Syrgkanis, Zhiwei Steven Wu

As a key technical tool, we introduce the concept of explorable actions, the actions which some incentive-compatible policy can recommend with non-zero probability.

no code implementations • 8 Feb 2016 • Vasilis Syrgkanis, Akshay Krishnamurthy, Robert E. Schapire

We provide the first oracle efficient sublinear regret algorithms for adversarial versions of the contextual bandit problem.

no code implementations • 4 Nov 2015 • Constantinos Daskalakis, Vasilis Syrgkanis

Our results for XOS valuations are enabled by a novel Follow-The-Perturbed-Leader algorithm for settings where the number of experts is infinite, and the payoff function of the learner is non-linear.

no code implementations • NeurIPS 2015 • Vasilis Syrgkanis, Alekh Agarwal, Haipeng Luo, Robert E. Schapire

We show that natural classes of regularized learning algorithms with a form of recency bias achieve faster convergence rates to approximate efficiency and to coarse correlated equilibria in multiplayer normal form games.

no code implementations • NeurIPS 2015 • Jason Hartline, Vasilis Syrgkanis, Eva Tardos

Recent price-of-anarchy analyses of games of complete information suggest that coarse correlated equilibria, which characterize outcomes resulting from no-regret learning dynamics, have near-optimal welfare.

Cannot find the paper you are looking for? You can
Submit a new open access paper.

Contact us on:
hello@paperswithcode.com
.
Papers With Code is a free resource with all data licensed under CC-BY-SA.